A novel ensemble model of automatic multilayer perceptron, random forest, and ZeroR for groundwater potential mapping.

Abstract

Declining levels of the water table in India have become a major concern, especially with climate change and burgeoning population compounding the problem and causing a perpetual state of water crisis. A better insight into the state of these precious resources is essential for their planned exploration and usage. This study introduces a novel machine learning ensemble model (ARZ ensemble), through an implementation of majority voting-based technique over its standalone classifier constituents, namely, Automatic Multilayer Perceptron (AutoMLP), random forest (RF), and ZeroR for undertaking the groundwater potential mapping for the Jabalpur district, Madhya Pradesh. Ten groundwater influencing factors (i.e., slope, rainfall, aspect, elevation, topographic wetness index, land use, lithology, distance from rivers, plan and profile curvature) and groundwater well locations from the study area were used to construct the spatial database. In order to validate the applicability of the proposed model, its performance was compared against a conventionally employed statistical method of Shannon's entropy (SE) model. The results revealed that the ARZ ensemble model (AUC: 0.8542) outperformed SE (AUC: 0.7639). The groundwater potential map revealed that approximately 4.18% of the region has very high groundwater potential, while 47.66% belongs to a low potential zone. Such information can hold solutions for a lot of the ailments afflicting these resources and can genuinely aid in the attempts to restore them to their natural state.